OCM image texture analysis for tissue classification

This paper proposes a texture analysis technique applied on human breast Optical Coherence Microscopy (OCM) images to classify different types of breast tissues. Local binary pattern (LBP) image features are extracted. In order to improve classification precision, a new variant of LBP feature, average LBP (ALBP) is proposed. The new LBP is integrated with the original LBP feature to improve classification precision. Our experiments show that by integrating a selected set of LBP and ALBP features, very high classification accuracy is achieved using a AdaBoost meta classifier combined with neural network weak classifiers.